Paleo-earthquake studies on the eastern section of the Kunlun fault   总被引：1，自引：0，他引：1  

李春峰  贺群禄  赵国光 《地震学报(英文版)》2005,18(1):64-71

Introduction East Kunlun active fault is one of the largest sinistral slip fault zones in northern Tibetan Pla-teau. The fault tails primarily after the ancient eastern Kunlun suture zone, which was reactivatedby the northward subduction of the Indian plate beneath the Eurasian plate. The western end of thefault starts near the western flank of the Buxedaban peak in Qinghai Province. The fault then ex-tends eastwards through the Kusai Lake, Xidatan, Dongdatan, Alag Lake, Tuosuo Lak…  相似文献   

Machine learning for pore-water pressure time-series prediction: Application of recurrent neural networks     

Xin Wei  Lulu Zhang  Hao-Qing Yang  Limin Zhang  Yang-Ping Yao 《地学前缘(英文版)》2021,12(1):453-467

Knowledge of pore-water pressure(PWP)variation is fundamental for slope stability.A precise prediction of PWP is difficult due to complex physical mechanisms and in situ natural variability.To explore the applicability and advantages of recurrent neural networks(RNNs)on PWP prediction,three variants of RNNs,i.e.,standard RNN,long short-term memory(LSTM)and gated recurrent unit(GRU)are adopted and compared with a traditional static artificial neural network(ANN),i.e.,multi-layer perceptron(MLP).Measurements of rainfall and PWP of representative piezometers from a fully instrumented natural slope in Hong Kong are used to establish the prediction models.The coefficient of determination(R^2)and root mean square error(RMSE)are used for model evaluations.The influence of input time series length on the model performance is investigated.The results reveal that MLP can provide acceptable performance but is not robust.The uncertainty bounds of RMSE of the MLP model range from 0.24 kPa to 1.12 k Pa for the selected two piezometers.The standard RNN can perform better but the robustness is slightly affected when there are significant time lags between PWP changes and rainfall.The GRU and LSTM models can provide more precise and robust predictions than the standard RNN.The effects of the hidden layer structure and the dropout technique are investigated.The single-layer GRU is accurate enough for PWP prediction,whereas a double-layer GRU brings extra time cost with little accuracy improvement.The dropout technique is essential to overfitting prevention and improvement of accuracy.  相似文献   

循环神经网络在雷达临近预报中的应用          下载免费PDF全文

韩丰  龙明盛  李月安  薛峰  王建民 《应用气象学报》2019,30(1):61-69

该文将循环神经网络（recurrent neural network,RNN）应用于雷达临近预报。使用预测循环神经网络（predictive RNN）架构,利用雷达历史组合反射率因子建模,给出雷达组合反射率因子未来1 h的预报结果。预测循环神经网络的核心是在长短时记忆单元（long short-term memory,LSTM）中增加时空记忆模块,能够提取雷达回波不同尺度的空间特征,配合循环神经网络架构,可以有效解决反射率因子预测问题。北京大兴雷达和广州雷达长时间序列的独立检验结果和2个强对流天气个例检验结果表明:该方法和传统的基于交叉相关法的1 h雷达外推临近预报相比,在20 dBZ和30 dBZ检验项目内,临界成功指数（CSI）可以提升0.15~0.30,命中率（POD）提高0.15~0.25,虚警率（FAR）降低0.15~0.20,该方法对反射率因子强度变化有一定预报能力。  相似文献   

东昆仑活动断裂带东段古地震活动特征   总被引：12，自引：0，他引：12       下载免费PDF全文

李春峰  贺群禄  赵国光 《地震学报》2005,27(1):60-67

东昆仑活动断裂托索湖——玛曲以东肯定那一带， 可据阿尼玛卿玛积峰为界再分为花石峡段和玛沁段两个在几何上不连续的段落. 两段在表征断层全新世活动特征的古地震事件方面有明显差异， 花石峡段的地震活动性明显高于玛沁段的地震活动性. 古地震研究表明， 花石峡段上3次强震活动相邻两次地震发生的时间间隔分别约为500 a和640 a， 玛沁段上最近两次古地震事件间大致有1 000 a左右的时间间隔. 根据断层平均滑动速率计算的花石峡段7.5级地震的平均复发间隔为411~608 a， 相对应的同震平均水平位错约为（5.75plusmn;0.57）m. 虽然玛沁段的地震活动性较弱， 但由于该段上最近一次地震事件离现在较为久远， 已经积累的应变能应该使我们对其未来地震危险性的分析有足够重视.   相似文献   

一种气候预测综合决策的方法——递归正权综合决策法   总被引：2，自引：0，他引：2  

项静恬  陈国珍  刘海波  赵振国 《大气科学》1999,23(5):551-558

根据气候预测的特点，提供了以误差平方和为风险函数，以正权综合为模式的多途径气候预测决策方案。不仅从理论上论证了几种正权方法的优性，还提供了递归技巧，进一步提高了正权综合的预测精度。对1997年汛期降水预测所做的综合决策表明，该方法具有较好的综合决策能力。  相似文献   

Sub-Alfvénic flows in the quiet and recurrent solar winds     

Gong-liang Zhang 《Chinese Astronomy and Astrophysics》1996,20(4):482-486

Observed instances are given in this paper to show that sub-Alfvénic flow can be formed in the quiet and recurrent low-speed solar wind streams. This kind of flow appears in regions with abnormal enhancement of Alfvénic speed and is associated with a specific type of magnetic configuration.  相似文献   

The 1978 outburst of the recurrent nova WZ Sagittae     

Hao Xiang-liang  Mei Bao 《Chinese Astronomy and Astrophysics》1987,11(4):288-290

We give the results of photographic observations of the recurrent nova WZ Sge during its 1978 outburst, between December 5 and 25, using the double astrograph of Beijing Observatory. We discuss the observed properties and calculate the total energy released during the outburst to be about 1.07 (+40) erg. We estimate that the next outburst will occur around the year 2011.  相似文献   

MARC: a robust method for multiple-aspect trajectory classification via space,time, and semantic embeddings     

Lucas May Petry  Camila Leite Da Silva  Andrea Esuli  Chiara Renso  Vania Bogorny 《International journal of geographical information science》2020,34(7):1428-1450

ABSTRACT

The increasing popularity of Location-Based Social Networks (LBSNs) and the semantic enrichment of mobility data in several contexts in the last years has led to the generation of large volumes of trajectory data. In contrast to GPS-based trajectories, LBSN and context-aware trajectories are more complex data, having several semantic textual dimensions besides space and time, which may reveal interesting mobility patterns. For instance, people may visit different places or perform different activities depending on the weather conditions. These new semantically rich data, known as multiple-aspect trajectories, pose new challenges in trajectory classification, which is the problem that we address in this paper. Existing methods for trajectory classification cannot deal with the complexity of heterogeneous data dimensions or the sequential aspect that characterizes movement. In this paper we propose MARC, an approach based on attribute embedding and Recurrent Neural Networks (RNNs) for classifying multiple-aspect trajectories, that tackles all trajectory properties: space, time, semantics, and sequence. We highlight that MARC exhibits good performance especially when trajectories are described by several textual/categorical attributes. Experiments performed over four publicly available datasets considering the Trajectory-User Linking (TUL) problem show that MARC outperformed all competitors, with respect to accuracy, precision, recall, and F1-score.  相似文献   

顾及地理-语义动态的城市热点预测框架     

沙恒宇  金广垠  程光权  黄金才  吴克宇 《地球信息科学学报》2022,24(1):25-37

城市热点时空预测是城市管理和智慧城市建设的一项长期而富有挑战性的任务。准确地进行城市热点时空预测可以提高城市规划、调度和安全保障能力并降低资源消耗。现有的区域级深度时空预测方法主要利用基于地理网格的图像、给定的网络结构或额外的数据来获取时空动态。通过从原始数据中挖掘出潜在的自语义信息,并将其与基于地理空间的网格图像融合,也可以提高时空预测的性能,基于此,本文提出了一种新的深度学习方法地理语义集成神经网络(GSEN),将地理预测神经网络和语义预测神经网络相叠加。GSEN模型综合了预测递归神经网络（PredRNN）、图卷积预测递归神经网络（GC-PredRNN）和集成层的结构,从不同的角度捕捉时空动态。并且该模型还可以与现实世界中一些潜在的高层动态进行关联,而不需要任何额外的数据。最终在3个不同领域的实际数据集上对本文提出的模型进行了评估,均取得了很好的预测效果,实验结果表明GSEN模型在不同城市热点时空预测任务中的推广性和有效性,利用该模型可以更好地进行城市热点时空预测,解决一系列如犯罪、火灾、网约车预订等等现代城市发展中亟需解决的相关问题。  相似文献   

基于深度学习和时空特征融合的海洋渔船密度预测方法          下载免费PDF全文

丁依婷  胡志远  董帝渤 《应用海洋学学报》2024,43(2):350-359

为了从海量渔船轨迹数据中挖掘隐含的信息和知识,进而为渔业行政主管部门的决策提供科学依据,本研究以AIS渔船轨迹数据为研究对象,提出了一种基于深度学习和面向时空特征融合的海洋渔船密度预测方法：首先,利用渔船轨迹数据集对渔船行驶区域进行网格划分;其次,筛选出渔船高密度区域进行研究,避免数据稀疏性问题;再次,根据渔船轨迹数据的时空分析,构建三维时空融合矩阵;最后,通过卷积循环神经网络模型捕获渔船分布的时间和空间特征,并利用卷积神经网络的堆叠加强对空间特征的学习。实验通过东海海域渔船真实轨迹数据进行具体测试,结果表明渔船密度预测值与真实值非常接近,平均绝对误差为4×10-4,模型较好地拟合了渔船密度分布特征,有效地提高了渔船捕捞热点预测的准确性和鲁棒性。  相似文献